ROOTPLOIT
Server: LiteSpeed
System: Linux server71.web-hosting.com 4.18.0-513.18.1.lve.el8.x86_64 #1 SMP Thu Feb 22 12:55:50 UTC 2024 x86_64
User: niphet (1079)
PHP: 5.3.29
Disabled: NONE
Upload Files
File: //lib64/python3.8/email/__pycache__/_header_value_parser.cpython-38.opt-1.pyc
U

e5dϡ	@sdZddlZddlZddlZddlmZddlmZddlm	Z
ddlmZddlmZe
dZee
d	BZe
d
ZeeBZee
dZee
dZee
d
Be
dZeeBZee
dBZeeBZee
dZddZedejejBZGdddeZGdddeZ GdddeZ!GdddeZ"GdddeZ#Gddde Z$Gdd d eZ%Gd!d"d"eZ&Gd#d$d$eZ'Gd%d&d&eZ(Gd'd(d(e(Z)Gd)d*d*e Z*Gd+d,d,eZ+Gd-d.d.eZ,Gd/d0d0eZ-Gd1d2d2eZ.Gd3d4d4eZ/Gd5d6d6eZ0Gd7d8d8eZ1Gd9d:d:eZ2Gd;d<d<eZ3Gd=d>d>eZ4Gd?d@d@eZ5GdAdBdBeZ6GdCdDdDeZ7GdEdFdFeZ8GdGdHdHeZ9GdIdJdJeZ:GdKdLdLe"Z;GdMdNdNeZ<GdOdPdPeZ=GdQdRdReZ>GdSdTdTeZ?GdUdVdVe?Z@GdWdXdXeZAGdYdZdZeZBGd[d\d\eZCGd]d^d^eZDGd_d`d`eZEGdadbdbeEZFGdcddddeEZGGdedfdfeZHGdgdhdheZIGdidjdjeZJGdkdldleJZKGdmdndneKZLGdodpdpeZMGdqdrdreNZOGdsdtdteOZPGdudvdveOZQGdwdxdxePZRGdydzdzejSZTeQdd{ZUeQd|d}ZVeQd~dZWedXdYejZZ[edXe\dYej]Z^edj_Z`edXe\dYej]ZaedXe\dYej]ZbedXe\dYej]ZcddZdddZeddZfddZgddZhddZiddZjddZkddZlddZmddZnddZoddZpddZqddZrddZsddZtddZuddZvddZwddZxddZyddZzddZ{ddZ|ddZ}ddZ~ddZddZddZddZddÄZddńZddDŽZddɄZdd˄Zdd̈́ZddτZddфZddӄZddՄZddׄZddلZddۄZdd݄Zdd߄ZddZddZddZddZddZddZddZddZddZddZddZddZdS)alHeader value parser implementing various email-related RFC parsing rules.

The parsing methods defined in this module implement various email related
parsing rules.  Principal among them is RFC 5322, which is the followon
to RFC 2822 and primarily a clarification of the former.  It also implements
RFC 2047 encoded word decoding.

RFC 5322 goes to considerable trouble to maintain backward compatibility with
RFC 822 in the parse phase, while cleaning up the structure on the generation
phase.  This parser supports correct RFC 5322 generation by tagging white space
as folding white space only when folding is allowed in the non-obsolete rule
sets.  Actually, the parser is even more generous when accepting input than RFC
5322 mandates, following the spirit of Postel's Law, which RFC 5322 encourages.
Where possible deviations from the standard are annotated on the 'defects'
attribute of tokens that deviate.

The general structure of the parser follows RFC 5322, and uses its terminology
where there is a direct correspondence.  Where the implementation requires a
somewhat different structure than that used by the formal grammar, new terms
that mimic the closest existing terms are used.  Thus, it really helps to have
a copy of RFC 5322 handy when studying this code.

Input to the parser is a string that has already been unfolded according to
RFC 5322 rules.  According to the RFC this unfolding is the very first step, and
this parser leaves the unfolding step to a higher level message parser, which
will have already detected the line breaks that need unfolding while
determining the beginning and end of each header.

The output of the parser is a TokenList object, which is a list subclass.  A
TokenList is a recursive data structure.  The terminal nodes of the structure
are Terminal objects, which are subclasses of str.  These do not correspond
directly to terminal objects in the formal grammar, but are instead more
practical higher level combinations of true terminals.

All TokenList and Terminal objects have a 'value' attribute, which produces the
semantically meaningful value of that part of the parse subtree.  The value of
all whitespace tokens (no matter how many sub-tokens they may contain) is a
single space, as per the RFC rules.  This includes 'CFWS', which is herein
included in the general class of whitespace tokens.  There is one exception to
the rule that whitespace tokens are collapsed into single spaces in values: in
the value of a 'bare-quoted-string' (a quoted-string with no leading or
trailing whitespace), any whitespace that appeared between the quotation marks
is preserved in the returned value.  Note that in all Terminal strings quoted
pairs are turned into their unquoted values.

All TokenList and Terminal objects also have a string value, which attempts to
be a "canonical" representation of the RFC-compliant form of the substring that
produced the parsed subtree, including minimal use of quoted pair quoting.
Whitespace runs are not collapsed.

Comment tokens also have a 'content' attribute providing the string found
between the parens (including any nested comments) with whitespace preserved.

All TokenList and Terminal objects have a 'defects' attribute which is a
possibly empty list all of the defects found while creating the token.  Defects
may appear on any token in the tree, and a composite list of all defects in the
subtree is available through the 'all_defects' attribute of any node.  (For
Terminal notes x.defects == x.all_defects.)

Each object in a parse tree is called a 'token', and each has a 'token_type'
attribute that gives the name from the RFC 5322 grammar that it represents.
Not all RFC 5322 nodes are produced, and there is one non-RFC 5322 node that
may be produced: 'ptext'.  A 'ptext' is a string of printable ascii characters.
It is returned in place of lists of (ctext/quoted-pair) and
(qtext/quoted-pair).

XXX: provide complete list of token types.
N)	hexdigits)
itemgetter)_encoded_words)errors)utilsz 	(z
()<>@,:;.\"[].z."(z/?=z*'%%cCs dt|dddddS)N"\\\z\")strreplacevaluer2/usr/lib64/python3.8/email/_header_value_parser.pyquote_string`srz
   =\?            # literal =?
   [^?]*          # charset
   \?             # literal ?
   [qQbB]         # literal 'q' or 'b', case insensitive
   \?             # literal ?
  .*?             # encoded word
  \?=             # literal ?=
cseZdZdZdZdZfddZddZfddZe	d	d
Z
e	ddZd
dZe	ddZ
e	ddZddZdddZdddZdddZZS)	TokenListNTcstj||g|_dSN)super__init__defects)selfargskw	__class__rrryszTokenList.__init__cCsddd|DS)Ncss|]}t|VqdSrr
.0xrrr	<genexpr>~sz$TokenList.__str__.<locals>.<genexpr>joinrrrr__str__}szTokenList.__str__csd|jjtSNz{}({})formatr__name__r__repr__r&rrrr,s
zTokenList.__repr__cCsddd|DS)Nrcss|]}|jr|jVqdSrrr rrrr#sz"TokenList.value.<locals>.<genexpr>r$r&rrrrszTokenList.valuecCstdd|D|jS)Ncss|]}|jVqdSr)all_defectsr rrrr#sz(TokenList.all_defects.<locals>.<genexpr>)sumrr&rrrr-szTokenList.all_defectscCs|dSNr)startswith_fwsr&rrrr0szTokenList.startswith_fwscCstdd|DS)zATrue if all top level tokens of this part may be RFC2047 encoded.css|]}|jVqdSr)
as_ew_allowed)r!partrrrr#sz*TokenList.as_ew_allowed.<locals>.<genexpr>)allr&rrrr1szTokenList.as_ew_allowedcCsg}|D]}||jq|Sr)extendcomments)rr5tokenrrrr5szTokenList.commentscCst||dS)Npolicy)_refold_parse_treerr8rrrfoldszTokenList.foldrcCst|j|ddS)Nindent)printppstrrr=rrrpprintszTokenList.pprintcCsd|j|dS)N
r<)r%_ppr@rrrr?szTokenList.ppstrccszd||jj|jV|D]4}t|ds:|d|Vq||dEdHq|jrdd|j}nd}d||VdS)Nz{}{}/{}(rCz*    !! invalid element in token list: {!r}z    z Defects: {}rz{}){})r*rr+
token_typehasattrrCr)rr=r6ZextrarrrrCs

z
TokenList._pp)r)r)r)r+
__module____qualname__rDsyntactic_breakew_combine_allowedrr'r,propertyrr-r0r1r5r;rAr?rC
__classcell__rrrrrss&





rc@s$eZdZeddZeddZdS)WhiteSpaceTokenListcCsdSN rr&rrrrszWhiteSpaceTokenList.valuecCsdd|DS)NcSsg|]}|jdkr|jqS)comment)rDcontentr rrr
<listcomp>s
z0WhiteSpaceTokenList.comments.<locals>.<listcomp>rr&rrrr5szWhiteSpaceTokenList.commentsN)r+rFrGrJrr5rrrrrLs
rLc@seZdZdZdS)UnstructuredTokenListunstructuredNr+rFrGrDrrrrrRsrRc@seZdZdZdS)PhrasephraseNrTrrrrrUsrUc@seZdZdZdS)WordZwordNrTrrrrrWsrWc@seZdZdZdS)CFWSListcfwsNrTrrrrrXsrXc@seZdZdZdS)AtomatomNrTrrrrrZsrZc@seZdZdZdZdS)Tokenr6FN)r+rFrGrDZencode_as_ewrrrrr\sr\c@seZdZdZdZdZdZdS)EncodedWordencoded-wordN)r+rFrGrDctecharsetlangrrrrr]sr]c@s4eZdZdZeddZeddZeddZdS)	QuotedString
quoted-stringcCs"|D]}|jdkr|jSqdSNbare-quoted-stringrDrrr"rrrrPs
zQuotedString.contentcCs>g}|D]*}|jdkr&|t|q||jqd|S)Nrer)rDappendr
rr%)rresr"rrrquoted_values
zQuotedString.quoted_valuecCs"|D]}|jdkr|jSqdSrdrfrr6rrrstripped_values
zQuotedString.stripped_valueN)r+rFrGrDrJrPrjrlrrrrrbs

	rbc@s$eZdZdZddZeddZdS)BareQuotedStringrecCstddd|DS)Nrcss|]}t|VqdSrrr rrrr#sz+BareQuotedString.__str__.<locals>.<genexpr>)rr%r&rrrr'szBareQuotedString.__str__cCsddd|DS)Nrcss|]}t|VqdSrrr rrrr#sz)BareQuotedString.value.<locals>.<genexpr>r$r&rrrrszBareQuotedString.valueN)r+rFrGrDr'rJrrrrrrmsrmc@s8eZdZdZddZddZeddZedd	Zd
S)CommentrOcs(dtdgfddDdgggS)Nrrcsg|]}|qSr)quoter r&rrrQsz#Comment.__str__.<locals>.<listcomp>))r%r.r&rr&rr'szComment.__str__cCs2|jdkrt|St|ddddddS)NrOrrrz\(rpz\))rDr
r)rrrrrros
z
Comment.quotecCsddd|DS)Nrcss|]}t|VqdSrrr rrrr#sz"Comment.content.<locals>.<genexpr>r$r&rrrrPszComment.contentcCs|jgSr)rPr&rrrr5szComment.commentsN)	r+rFrGrDr'rorJrPr5rrrrrns
rnc@s4eZdZdZeddZeddZeddZdS)	AddressListzaddress-listcCsdd|DS)NcSsg|]}|jdkr|qS)addressrDr rrrrQ's
z)AddressList.addresses.<locals>.<listcomp>rr&rrr	addresses%szAddressList.addressescCstdd|DgS)Ncss|]}|jdkr|jVqdSrrNrD	mailboxesr rrrr#+s
z(AddressList.mailboxes.<locals>.<genexpr>r.r&rrrrw)s
zAddressList.mailboxescCstdd|DgS)Ncss|]}|jdkr|jVqdSrurD
all_mailboxesr rrrr#0s
z,AddressList.all_mailboxes.<locals>.<genexpr>rxr&rrrrz.s
zAddressList.all_mailboxesN)r+rFrGrDrJrtrwrzrrrrrq!s

rqc@s4eZdZdZeddZeddZeddZdS)	AddressrrcCs|djdkr|djSdS)NrgrouprDdisplay_namer&rrrr~8szAddress.display_namecCs4|djdkr|dgS|djdkr*gS|djSNrmailboxinvalid-mailboxrvr&rrrrw=s

zAddress.mailboxescCs:|djdkr|dgS|djdkr0|dgS|djSrryr&rrrrzEs


zAddress.all_mailboxesN)r+rFrGrDrJr~rwrzrrrrr{4s

r{c@s(eZdZdZeddZeddZdS)MailboxListmailbox-listcCsdd|DS)NcSsg|]}|jdkr|qS)rrsr rrrrQSs
z)MailboxList.mailboxes.<locals>.<listcomp>rr&rrrrwQszMailboxList.mailboxescCsdd|DS)NcSsg|]}|jdkr|qS))rrrsr rrrrQWs
z-MailboxList.all_mailboxes.<locals>.<listcomp>rr&rrrrzUszMailboxList.all_mailboxesNr+rFrGrDrJrwrzrrrrrMs

rc@s(eZdZdZeddZeddZdS)	GroupList
group-listcCs |r|djdkrgS|djSNrrrvr&rrrrw_szGroupList.mailboxescCs |r|djdkrgS|djSrryr&rrrrzeszGroupList.all_mailboxesNrrrrrr[s

rc@s4eZdZdZeddZeddZeddZdS)	Groupr|cCs|djdkrgS|djSNrrvr&rrrrwpszGroup.mailboxescCs|djdkrgS|djSrryr&rrrrzvszGroup.all_mailboxescCs
|djSr/)r~r&rrrr~|szGroup.display_nameN)r+rFrGrDrJrwrzr~rrrrrls

rc@sLeZdZdZeddZeddZeddZedd	Zed
dZ	dS)
NameAddr	name-addrcCst|dkrdS|djSNr)lenr~r&rrrr~szNameAddr.display_namecCs
|djSN
local_partr&rrrrszNameAddr.local_partcCs
|djSrdomainr&rrrrszNameAddr.domaincCs
|djSr)router&rrrrszNameAddr.routecCs
|djSr	addr_specr&rrrrszNameAddr.addr_specN
r+rFrGrDrJr~rrrrrrrrrs



rc@s@eZdZdZeddZeddZeddZedd	Zd
S)	AngleAddrz
angle-addrcCs"|D]}|jdkr|jSqdSN	addr-spec)rDrrgrrrrs
zAngleAddr.local_partcCs"|D]}|jdkr|jSqdSrrDrrgrrrrs
zAngleAddr.domaincCs"|D]}|jdkr|jSqdS)N	obs-route)rDdomainsrgrrrrs
zAngleAddr.routecCs<|D]2}|jdkr|jr"|jSt|j|jSqdS)Nrz<>)rDrrrrgrrrrs

zAngleAddr.addr_specN)	r+rFrGrDrJrrrrrrrrrs


rc@seZdZdZeddZdS)ObsRoutercCsdd|DS)NcSsg|]}|jdkr|jqSrrr rrrrQs
z$ObsRoute.domains.<locals>.<listcomp>rr&rrrrszObsRoute.domainsN)r+rFrGrDrJrrrrrrsrc@sLeZdZdZeddZeddZeddZedd	Zed
dZ	dS)
MailboxrcCs|djdkr|djSdSNrrr}r&rrrr~szMailbox.display_namecCs
|djSr/rr&rrrrszMailbox.local_partcCs
|djSr/rr&rrrrszMailbox.domaincCs|djdkr|djSdSr)rDrr&rrrrsz
Mailbox.routecCs
|djSr/rr&rrrrszMailbox.addr_specNrrrrrrs



rc@s,eZdZdZeddZeZZZZ	dS)InvalidMailboxrcCsdSrrr&rrrr~szInvalidMailbox.display_nameNrrrrrrs
rcs(eZdZdZdZefddZZS)DomainrFcsdtjSNrr%rrsplitr&rrrrsz
Domain.domain)r+rFrGrDr1rJrrKrrrrrsrc@seZdZdZdS)DotAtomdot-atomNrTrrrrrsrc@seZdZdZdZdS)DotAtomTextz
dot-atom-textTNr+rFrGrDr1rrrrrsrc@seZdZdZdZdS)
NoFoldLiteralzno-fold-literalFNrrrrrrsrc@sDeZdZdZdZeddZeddZeddZed	d
Z	dS)AddrSpecrFcCs
|djSr/rr&rrrr
szAddrSpec.local_partcCst|dkrdS|djS)Nr)rrr&rrrrszAddrSpec.domaincCs<t|dkr|djS|dj|dj|djS)Nrrrr)rrrstriplstripr&rrrrs
zAddrSpec.valuecCsLt|j}t|t|tkr*t|j}n|j}|jdk	rH|d|jS|S)N@)setrr
DOT_ATOM_ENDSrr)rZnamesetZlprrrrs

zAddrSpec.addr_specN)
r+rFrGrDr1rJrrrrrrrrrs


rc@seZdZdZdZdS)ObsLocalPartzobs-local-partFNrrrrrr&srcs4eZdZdZdZeddZefddZZS)DisplayNamezdisplay-nameFcCst|}t|dkr|jS|djdkr4|dn*|ddjdkr^t|ddd|d<|djdkrv|n*|ddjdkrt|ddd|d<|jS)NrrYrr)rrrrDpop)rrirrrr~1s
zDisplayName.display_namecsd}|jrd}n|D]}|jdkrd}qt|dkr|rd}}|djdks`|ddjdkrdd}|djdks|ddjdkrd}|t|j|StjSdS)	NFTrcrrrYrNr)rrDrrr~rr)rror"ZpreZpostrrrrBs
  zDisplayName.value)	r+rFrGrDrIrJr~rrKrrrrr,s
rc@s,eZdZdZdZeddZeddZdS)	LocalPartz
local-partFcCs&|djdkr|djS|djSdS)Nrrc)rDrjrr&rrrr[s
zLocalPart.valuecCstg}t}d}|dtgD]}|jdkr,q|r\|jdkr\|djdkr\t|dd|d<t|t}|r|jdkr|djdkr|t|ddn
|||d}|}qt|dd}|jS)NFrrYdotrr)DOTrDr
isinstancerhr)rriZlastZ
last_is_tltokZis_tlrrrrbs(


zLocalPart.local_partN)r+rFrGrDr1rJrrrrrrrVs
rcs4eZdZdZdZefddZeddZZS)
DomainLiteralzdomain-literalFcsdtjSrrr&rrrrszDomainLiteral.domaincCs"|D]}|jdkr|jSqdS)Nptextrfrgrrrips
zDomainLiteral.ip)	r+rFrGrDr1rJrrrKrrrrrzsrc@seZdZdZdZdZdS)MIMEVersionzmime-versionN)r+rFrGrDmajorminorrrrrrsrc@s4eZdZdZdZdZdZeddZeddZ	dS)		Parameter	parameterFus-asciicCs|jr|djSdSr)	sectionednumberr&rrrsection_numberszParameter.section_numbercCsf|D]\}|jdkr|jS|jdkr|D]4}|jdkr*|D] }|jdkr<|jSq<q*qdS)Nrrcrer)rDrlrkrrrparam_values




zParameter.param_valueN)
r+rFrGrDrextendedr`rJrrrrrrrs
rc@seZdZdZdS)InvalidParameterinvalid-parameterNrTrrrrrsrc@seZdZdZeddZdS)	Attribute	attributecCs$|D]}|jdr|jSqdS)Nattrtext)rDendswithrrkrrrrlszAttribute.stripped_valueNr+rFrGrDrJrlrrrrrsrc@seZdZdZdZdS)SectionsectionN)r+rFrGrDrrrrrrsrc@seZdZdZeddZdS)ValuercCs2|d}|jdkr|d}|jdr,|jS|jS)NrrYr)rcrzextended-attribute)rDrrlrrkrrrrls
zValue.stripped_valueNrrrrrrsrc@s(eZdZdZdZeddZddZdS)MimeParametersmime-parametersFc
csi}|D]T}|jdsq|djdkr*q|dj}||krHg||<|||j|fq|D]~\}}t|tdd}|dd}|j	}|j
st|dkr|dddkr|ddjt
d|dd}g}d}|D]\}	}
|	|kr(|
j
s|
jt
dqn|
jt
d|d7}|
j}|
j
rztj|}Wn&tk
rttjj|d	d
}YnRXz||d}Wn"tk
r|dd}YnXt|r|
jt
||qd
|}||fVqfdS)Nrrr)keyrz.duplicate parameter name; duplicate(s) ignoredz+duplicate parameter name; duplicate ignoredz(inconsistent RFC2231 parameter numberingzlatin-1)encodingsurrogateescaperr)rDrrstriprhritemssortedrr`rrrrInvalidHeaderDefectrurllibparseZunquote_to_bytesUnicodeEncodeErrorZunquotedecodeLookupErrorr_has_surrogatesUndecodableBytesDefectr%)rparamsr6namepartsZfirst_paramr`Zvalue_partsirparamrrrrrs`



zMimeParameters.paramscCsTg}|jD].\}}|r.|d|t|q
||q
d|}|rPd|SdS)N{}={}z; rNr)rrhr*rr%)rrrrrrrr's
zMimeParameters.__str__N)r+rFrGrDrHrJrr'rrrrrs

Erc@seZdZdZeddZdS)ParameterizedHeaderValueFcCs&t|D]}|jdkr|jSqiS)Nr)reversedrDrrkrrrr-s
zParameterizedHeaderValue.paramsN)r+rFrGrHrJrrrrrr'src@seZdZdZdZdZdZdS)ContentTypezcontent-typeFtextZplainN)r+rFrGrDr1maintypesubtyperrrrr5src@seZdZdZdZdZdS)ContentDispositionzcontent-dispositionFN)r+rFrGrDr1content_dispositionrrrrr<src@seZdZdZdZdZdS)ContentTransferEncodingzcontent-transfer-encodingFZ7bitN)r+rFrGrDr1r_rrrrrBsrc@seZdZdZdZdS)HeaderLabelzheader-labelFNrrrrrrHsrc@seZdZdZdZddZdS)MsgIDzmsg-idFcCst||jSr)r
linesepr:rrrr;Qsz
MsgID.foldN)r+rFrGrDr1r;rrrrrMsrc@seZdZdZdS)	MessageIDz
message-idNrTrrrrrVsrc@seZdZdZdS)InvalidMessageIDzinvalid-message-idNrTrrrrrZsrc@seZdZdZdS)HeaderheaderNrTrrrrr^srcsreZdZdZdZdZfddZfddZddZe	dd	Z
dfdd	Zd
dZe	ddZ
ddZZS)TerminalTcst||}||_g|_|Sr)r__new__rDr)clsrrDrrrrrlszTerminal.__new__csd|jjtSr(r)r&rrrr,rszTerminal.__repr__cCst|jjd|jdS)N/)r>rr+rDr&rrrrAuszTerminal.pprintcCs
t|jSr)listrr&rrrr-xszTerminal.all_defectsrc	s2d||jj|jt|js"dn
d|jgS)Nz
{}{}/{}({}){}rz {})r*rr+rDrr,rr@rrrrC|szTerminal._ppcCsdSrrr&rrrpop_trailing_wsszTerminal.pop_trailing_wscCsgSrrr&rrrr5szTerminal.commentscCst||jfSr)r
rDr&rrr__getnewargs__szTerminal.__getnewargs__)r)r+rFrGr1rIrHrr,rArJr-rCrr5rrKrrrrrfs
	
rc@s eZdZeddZddZdS)WhiteSpaceTerminalcCsdSrMrr&rrrrszWhiteSpaceTerminal.valuecCsdS)NTrr&rrrr0sz!WhiteSpaceTerminal.startswith_fwsNr+rFrGrJrr0rrrrrs
rc@s eZdZeddZddZdS)
ValueTerminalcCs|Srrr&rrrrszValueTerminal.valuecCsdS)NFrr&rrrr0szValueTerminal.startswith_fwsNrrrrrrs
rc@s eZdZeddZddZdS)EWWhiteSpaceTerminalcCsdSrrr&rrrrszEWWhiteSpaceTerminal.valuecCsdSrrr&rrrr'szEWWhiteSpaceTerminal.__str__N)r+rFrGrJrr'rrrrrs
rc@seZdZdZdS)_InvalidEwErrorz1Invalid encoded word found while parsing headers.N)r+rFrG__doc__rrrrrsrr,list-separatorrzroute-component-markerz([{}]+)rz[^{}]+z[\x00-\x20\x7F]cCs>t|}|r|jt|t|r:|jtddS)z@If input token contains ASCII non-printables, register a defect.z*Non-ASCII characters found in header tokenN)_non_printable_finderrrhrZNonPrintableDefectrrr)xtextZnon_printablesrrr_validate_xtexts

rcCst|d^}}g}d}d}tt|D]L}||dkrJ|rDd}d}nd}q&|rTd}n|||krdq||||q&|d}d|d||dg||fS)akScan printables/quoted-pairs until endchars and return unquoted ptext.

    This function turns a run of qcontent, ccontent-without-comments, or
    dtext-with-quoted-printables into a single string by unquoting any
    quoted printables.  It returns the string, the remaining value, and
    a flag that is True iff there were any quoted printables decoded.

    rFrTrN)
_wsp_splitterrangerrhr%)rendcharsZfragment	remainderZvcharsescapehad_qpposrrr_get_ptext_to_endcharss$	rcCs.|}t|dt|t|d}||fS)zFWS = 1*WSP

    This isn't the RFC definition.  We're using fws to represent tokens where
    folding can be done, but when we are parsing the *un*folding has already
    been done so we don't need to watch out for CRLF.

    Nfws)rrr)rZnewvaluerrrrget_fwssrc
	Cst}|ds td||dddd^}}||ddkrXtd|d|}t|dkr|dtkr|dtkr|	d	dkr|dd^}}|d|}t|dkr|j
td
||_
d|}ztd|d\}}}}	Wn*ttfk
r*td|j
YnX||_||_|j
|	|r|dtkrrt|\}
}||
qDt|d^}}t|d}t|||d|}qD|r|dtkr|j
td
||fS)zE encoded-word = "=?" charset "?" encoding "?" encoded-text "?="

    =?z"expected encoded word but found {}rNz?=rrr?zwhitespace inside encoded wordz!encoded word format invalid: '{}'vtextz.missing trailing whitespace after encoded-word)r]
startswithrHeaderParseErrorr*rr%rrcountrrhrr__ewr
ValueErrorKeyErrorrr`rar4WSPrrrr)
rZewrrZremstrrestrr`rarr6charsrrrrget_encoded_wordsd











r"cCsFt}|rB|dtkr0t|\}}||qd}|drzt|\}}Wn,tk
rfd}Yntjk
rzYnrXd}t	|dkr|dj
dkr|jtdd}|rt	|dkr|d	j
d
krt
|dd|d<||qt|d^}}|rt|r|d^}}t|d}t|||d|}q|S)
aOunstructured = (*([FWS] vchar) *WSP) / obs-unstruct
       obs-unstruct = *((*LF *CR *(obs-utext) *LF *CR)) / FWS)
       obs-utext = %d0 / obs-NO-WS-CTL / LF / CR

       obs-NO-WS-CTL is control characters except WSP/CR/LF.

    So, basically, we have printable runs, plus control characters or nulls in
    the obsolete syntax, separated by whitespace.  Since RFC 2047 uses the
    obsolete syntax in its specification, but requires whitespace on either
    side of the encoded words, I can see no reason to need to separate the
    non-printable-non-whitespace from the printable runs if they occur, so we
    parse this into xtext tokens separated by WSP tokens.

    Because an 'unstructured' value must by definition constitute the entire
    value, this 'get' routine does not return a remaining value, only the
    parsed TokenList.

    rTrFrrz&missing whitespace before encoded wordrr^rr)rRrrrhrr"rrrrrDrrrrrfc2047_matchersearch	partitionrrr%)rrSr6valid_ewZhave_wsrrrrrrget_unstructured?sJ





r(cCs*t|d\}}}t|d}t|||fS)actext = <printable ascii except \ ( )>

    This is not the RFC ctext, since we are handling nested comments in comment
    and unquoting quoted-pairs here.  We allow anything except the '()'
    characters, but if we find any ASCII other than the RFC defined printable
    ASCII, a NonPrintableDefect is added to the token's defects list.  Since
    quoted pairs are converted to their unquoted values, what is returned is
    a 'ptext' token.  In this case it is a WhiteSpaceTerminal, so it's value
    is ' '.

    z()r)rrrrr_rrrget_qp_ctexts
r+cCs*t|d\}}}t|d}t|||fS)aoqcontent = qtext / quoted-pair

    We allow anything except the DQUOTE character, but if we find any ASCII
    other than the RFC defined printable ASCII, a NonPrintableDefect is
    added to the token's defects list.  Any quoted pairs are converted to their
    unquoted values, so what is returned is a 'ptext' token.  In this case it
    is a ValueTerminal.

    r
r)rrrr)rrrget_qcontents

r,cCsNt|}|std||}|t|d}t|d}t|||fS)zatext = <matches _atext_matcher>

    We allow any non-ATOM_ENDS in atext, but add an InvalidATextDefect to
    the token's defects list if we find non-atext characters.
    zexpected atext but found '{}'Natext)_non_atom_end_matcherrrr*r|rrr)rmr-rrr	get_atexts
r0cCsr|ddkrtd|t}|dd}|rT|ddkrTt|\}}|||rB|ddkrB|dtkrt|\}}n|dddkr*d}z&t|\}}|j	t
d	d
}Wn"tjk
rt|\}}YnX|r6t|dkr6|djdkr6|d
jdkr6t
|dd|d<nt|\}}||qT|sb|j	t
d||fS||ddfS)zbare-quoted-string = DQUOTE *([FWS] qcontent) [FWS] DQUOTE

    A quoted-string without the leading or trailing white space.  Its
    value is the text between the quote marks, with whitespace
    preserved and quoted pairs decoded.
    rr
zexpected '"' but found '{}'rNrrFz!encoded word inside quoted stringTrrr#r^z"end of header inside quoted string)rrr*rmr,rhrrr"rrrrDr)rZbare_quoted_stringr6r'rrrget_bare_quoted_stringsL



r1cCs|r |ddkr td|t}|dd}|r|ddkr|dtkr\t|\}}n&|ddkrvt|\}}nt|\}}||q2|s|j	t
d||fS||ddfS)zcomment = "(" *([FWS] ccontent) [FWS] ")"
       ccontent = ctext / quoted-pair / comment

    We handle nested comments here, and quoted-pair in our qp-ctext routine.
    rrzexpected '(' but found '{}'rNrpzend of header inside comment)rrr*rnrrget_commentr+rhrr)rrOr6rrrr2s&
r2cCsPt}|rH|dtkrH|dtkr0t|\}}nt|\}}||q||fS)z,CFWS = (1*([FWS] comment) [FWS]) / FWS

    r)rXCFWS_LEADERrrr2rh)rrYr6rrrget_cfwssr4cCspt}|r,|dtkr,t|\}}||t|\}}|||rh|dtkrht|\}}||||fS)zquoted-string = [CFWS] <bare-quoted-string> [CFWS]

    'bare-quoted-string' is an intermediate class defined by this
    parser and not by the RFC grammar.  It is the quoted string
    without any attached CFWS.
    r)rbr3r4rhr1)rZ
quoted_stringr6rrrget_quoted_strings


r5cCst}|r,|dtkr,t|\}}|||rL|dtkrLtd||drzt	|\}}Wqtjk
rt
|\}}YqXnt
|\}}|||r|dtkrt|\}}||||fS)zPatom = [CFWS] 1*atext [CFWS]

    An atom could be an rfc2047 encoded word.
    rzexpected atom but found '{}'r)rZr3r4rh	ATOM_ENDSrrr*rr"r0)rr[r6rrrget_atoms&



r7cCst}|r|dtkr&td||rt|dtkrtt|\}}|||r&|ddkr&|t|dd}q&|dtkrtdd|||fS)z( dot-text = 1*atext *("." 1*atext)

    rz8expected atom at a start of dot-atom-text but found '{}'rrNrz4expected atom at end of dot-atom-text but found '{}')rr6rrr*r0rhr)rZ
dot_atom_textr6rrrget_dot_atom_text0s 

r8cCst}|dtkr(t|\}}|||drhzt|\}}Wqttjk
rdt|\}}YqtXnt|\}}|||r|dtkrt|\}}||||fS)z dot-atom = [CFWS] dot-atom-text [CFWS]

    Any place we can have a dot atom, we could instead have an rfc2047 encoded
    word.
    rr)	rr3r4rhrr"rrr8)rZdot_atomr6rrrget_dot_atomCs



r9cCs|dtkrt|\}}nd}|s,td|ddkrFt|\}}n*|dtkrdtd|nt|\}}|dk	r|g|dd<||fS)aword = atom / quoted-string

    Either atom or quoted-string may start with CFWS.  We have to peel off this
    CFWS first to determine which type of word to parse.  Afterward we splice
    the leading CFWS, if any, into the parsed sub-token.

    If neither an atom or a quoted-string is found before the next special, a
    HeaderParseError is raised.

    The token returned is either an Atom or a QuotedString, as appropriate.
    This means the 'word' level of the formal grammar is not represented in the
    parse tree; this is because having that extra layer when manipulating the
    parse tree is more confusing than it is helpful.

    rNz5Expected 'atom' or 'quoted-string' but found nothing.r
z1Expected 'atom' or 'quoted-string' but found '{}')r3r4rrr5SPECIALSr*r7)rleaderr6rrrget_word\s"r<cCst}zt|\}}||Wn(tjk
rH|jtdYnX|r|dtkr|ddkr|t|jt	d|dd}qJzt|\}}WnDtjk
r|dt
krt|\}}|jt	dnYnX||qJ||fS)a phrase = 1*word / obs-phrase
        obs-phrase = word *(word / "." / CFWS)

    This means a phrase can be a sequence of words, periods, and CFWS in any
    order as long as it starts with at least one word.  If anything other than
    words is detected, an ObsoleteHeaderDefect is added to the token's defect
    list.  We also accept a phrase that starts with CFWS followed by a dot;
    this is registered as an InvalidHeaderDefect, since it is not supported by
    even the obsolete grammar.

    zphrase does not start with wordrrzperiod in 'phrase'rNzcomment found without atom)rUr<rhrrrrPHRASE_ENDSrObsoleteHeaderDefectr3r4)rrVr6rrr
get_phrase~s4



r?cCsvt}d}|dtkr"t|\}}|s6td|zt|\}}Wn^tjk
rzt|\}}Wn6tjk
r|ddkr|dtkrt	}YnXYnX|dk	r|g|dd<|
||r4|ddks|dtkr4tt||\}}|j
dkr|j
tdn|j
td||d<z|jdWn(tk
rl|j
td	YnX||fS)
z= local-part = dot-atom / quoted-string / obs-local-part

    Nrz"expected local-part but found '{}'rinvalid-obs-local-partz<local-part is not dot-atom, quoted-string, or obs-local-partz,local-part is not a dot-atom (contains CFWS)asciiz)local-part contains non-ASCII characters))rr3r4rrr*r9r<r=rrhget_obs_local_partr
rDrrr>rencoderZNonASCIILocalPartDefect)rrr;r6obs_local_partrrrget_local_partsJ
 


rEcCst}d}|r(|ddks*|dtkr(|ddkrj|rL|jtd|td}|dd}q
nD|ddkr|t|dd	|dd}|jtd
d}q
|r|djdkr|jtd
zt	|\}}d}Wn4tj
k
r|dtkr
t|\}}YnX||q
|djdksX|djdkrj|djdkrj|jtd|djdks|djdkr|djdkr|jtd|jrd|_||fS)z' obs-local-part = word *("." word)
    Frrrzinvalid repeated '.'TrNmisplaced-specialz/'\' character outside of quoted-string/ccontentrrzmissing '.' between wordsrYz!Invalid leading '.' in local partr#z"Invalid trailing '.' in local partr@)
rr=rrhrrrrrDr<rr3r4)rrDZlast_non_ws_was_dotr6rrrrBsj 





rBcCs@t|d\}}}t|d}|r0|jtdt|||fS)a dtext = <printable ascii except \ [ ]> / obs-dtext
        obs-dtext = obs-NO-WS-CTL / quoted-pair

    We allow anything except the excluded characters, but if we find any
    ASCII other than the RFC defined printable ASCII, a NonPrintableDefect is
    added to the token's defects list.  Quoted pairs are converted to their
    unquoted values, so what is returned is a ptext token, in this case a
    ValueTerminal.  If there were quoted-printables, an ObsoleteHeaderDefect is
    added to the returned token's defect list.

    z[]rz(quoted printable found in domain-literal)rrrrhrr>r)rrrrrr	get_dtexts

rGcCs,|rdS|td|tdddS)NFz"end of input inside domain-literal]domain-literal-endT)rhrrr)rdomain_literalrrr_check_for_early_dl_endsrKcCsjt}|dtkr(t|\}}|||s6td|ddkrRtd||dd}t||rp||fS|tdd|dt	krt
|\}}||t|\}}||t||r||fS|dt	krt
|\}}||t||r||fS|ddkrtd	||tdd
|dd}|rb|dtkrbt|\}}||||fS)zB domain-literal = [CFWS] "[" *([FWS] dtext) [FWS] "]" [CFWS]

    rzexpected domain-literal[z6expected '[' at start of domain-literal but found '{}'rNzdomain-literal-startrHz4expected ']' at end of domain-literal but found '{}'rI)rr3r4rhrrr*rKrrrrG)rrJr6rrrget_domain_literalsH








rMcCsrt}d}|dtkr"t|\}}|s6td||ddkrvt|\}}|dk	rd|g|dd<||||fSzt|\}}Wn"tjk
rt	|\}}YnX|r|ddkrtd|dk	r|g|dd<|||rj|ddkrj|j
td|djd	kr*|d|dd<|rj|ddkrj|t
t	|d
d\}}||q*||fS)z] domain = dot-atom / domain-literal / obs-domain
        obs-domain = atom *("." atom))

    Nrzexpected domain but found '{}'rLrzInvalid Domainrz(domain is not a dot-atom (contains CFWS)rr)rr3r4rrr*rMrhr9r7rr>rDr)rrr;r6rrr
get_domain=sD




rNcCs|t}t|\}}|||r,|ddkrF|jtd||fS|tddt|dd\}}||||fS)z( addr-spec = local-part "@" domain

    rrz#addr-spec local part with no domainaddress-at-symbolrN)rrErhrrrrrN)rrr6rrr
get_addr_speccs


rPcCst}|rj|ddks"|dtkrj|dtkrFt|\}}||q|ddkr|t|dd}q|rz|ddkrtd||tt	|dd\}}|||r>|ddkr>|t|dd}|sq>|dtkrt|\}}|||ddkr|tt	|dd\}}||q|sNtd|ddkrltd	||t
dd
||ddfS)z obs-route = obs-domain-list ":"
        obs-domain-list = *(CFWS / ",") "@" domain *("," [CFWS] ["@" domain])

        Returns an obs-route token with the appropriate sub-tokens (that is,
        there is no obs-domain-list in the parse tree).
    rrrNrz(expected obs-route domain but found '{}'z%end of header while parsing obs-route:z4expected ':' marking end of obs-route but found '{}'zend-of-obs-route-marker)rr3r4rh
ListSeparatorrrr*RouteComponentMarkerrNr)rZ	obs_router6rrr
get_obs_routessF






rTcCst}|dtkr(t|\}}|||r8|ddkrHtd||tdd|dd}|ddkr|tdd|jt	d	|dd}||fSzt
|\}}Wnztjk
r0z"t|\}}|jtd
Wn(tjk
rtd|YnX||t
|\}}YnX|||r^|ddkr^|dd}n|jt	d|tdd|r|dtkrt|\}}||||fS)
z angle-addr = [CFWS] "<" addr-spec ">" [CFWS] / obs-angle-addr
        obs-angle-addr = [CFWS] "<" obs-route addr-spec ">" [CFWS]

    r<z"expected angle-addr but found '{}'zangle-addr-startrN>zangle-addr-endznull addr-spec in angle-addrz*obsolete route specification in angle-addrz.expected addr-spec or obs-route but found '{}'z"missing trailing '>' on angle-addr)
rr3r4rhrrr*rrrrPrTr>)rZ
angle_addrr6rrrget_angle_addrsT








rWcCs<t}t|\}}||dd|jdd|_||fS)z display-name = phrase

    Because this is simply a name-rule, we don't return a display-name
    token containing a phrase, but rather a display-name token with
    the content of the phrase.

    N)rr?r4r)rr~r6rrrget_display_names
rXcCst}d}|dtkr6t|\}}|s6td||ddkr|dtkr^td|t|\}}|s~td||dk	r|g|ddd<d}||t	|\}}|dk	r|g|dd<||||fS)z, name-addr = [display-name] angle-addr

    Nrz!expected name-addr but found '{}'rU)
rr3r4rrr*r=rXrhrW)rZ	name_addrr;r6rrr
get_name_addrs6

rYcCst}zt|\}}WnNtjk
rdzt|\}}Wn&tjk
r^td|YnXYnXtdd|jDrd|_|	|||fS)z& mailbox = name-addr / addr-spec

    zexpected mailbox but found '{}'css|]}t|tjVqdSr)rrrr rrrr#szget_mailbox.<locals>.<genexpr>r)
rrYrrrPr*anyr-rDrh)rrr6rrrget_mailboxs 
r[cCsdt}|r\|d|kr\|dtkrD|t|dd|dd}qt|\}}||q||fS)z Read everything up to one of the chars in endchars.

    This is outside the formal grammar.  The InvalidMailbox TokenList that is
    returned acts like a Mailbox, but the data attributes are None.

    rrFrN)rr=rhrr?)rrZinvalid_mailboxr6rrrget_invalid_mailboxsr\cCst}|r|ddkrzt|\}}||Wntjk
r<d}|dtkrt|\}}|rv|ddkr|||jtdn@t	|d\}}|dk	r|g|dd<|||jt
dnb|ddkr|jtdnBt	|d\}}|dk	r|g|dd<|||jt
dYnX|r|ddkr|d}d	|_t	|d\}}|||jt
d|r|ddkr|t
|d
d}q||fS)aJ mailbox-list = (mailbox *("," mailbox)) / obs-mbox-list
        obs-mbox-list = *([CFWS] ",") mailbox *("," [mailbox / CFWS])

    For this routine we go outside the formal grammar in order to improve error
    handling.  We recognize the end of the mailbox list only at the end of the
    value or at a ';' (the group terminator).  This is so that we can turn
    invalid mailboxes into InvalidMailbox tokens and continue parsing any
    remaining valid mailboxes.  We also allow all mailbox entries to be null,
    and this condition is handled appropriately at a higher level.

    r;Nz,;zempty element in mailbox-listzinvalid mailbox in mailbox-listrrrr)rr[rhrrr3r4rr>r\rrDr4rR)rZmailbox_listr6r;rrrrget_mailbox_listsX










r^cCst}|s$|jtd||fSd}|r|dtkrt|\}}|sl|jtd||||fS|ddkr||||fSt|\}}t|j	dkr|dk	r|||
||jtd||fS|dk	r|g|dd<||||fS)zg group-list = mailbox-list / CFWS / obs-group-list
        obs-group-list = 1*([CFWS] ",") [CFWS]

    zend of header before group-listNrzend of header in group-listr]zgroup-list with empty entries)rrrhrrr3r4r^rrzr4r>)rZ
group_listr;r6rrrget_group_listWs>







r_cCs t}t|\}}|r"|ddkr2td||||tdd|dd}|r|ddkr|tdd||ddfSt|\}}|||s|jt	d	n|ddkrtd
||tdd|dd}|r|dt
krt|\}}||||fS)z7 group = display-name ":" [group-list] ";" [CFWS]

    rrQz8expected ':' at end of group display name but found '{}'zgroup-display-name-terminatorrNr]zgroup-terminatorzend of header in groupz)expected ';' at end of group but found {})rrXrrr*rhrr_rrr3r4)rr|r6rrr	get_group|s8



r`cCsxt}zt|\}}WnNtjk
rdzt|\}}Wn&tjk
r^td|YnXYnX||||fS)a address = mailbox / group

    Note that counter-intuitively, an address can be either a single address or
    a list of addresses (a group).  This is why the returned Address object has
    a 'mailboxes' attribute which treats a single address as a list of length
    one.  When you need to differentiate between to two cases, extract the single
    element, which is either a mailbox or a group token.

    zexpected address but found '{}')r{r`rrr[r*rh)rrrr6rrrget_addresss
rac
Cst}|rzt|\}}||Wn tjk
rH}zd}|dtkrt|\}}|rj|ddkr|||jtdnFt	|d\}}|dk	r|g|dd<|t
|g|jtdnh|ddkr|jtdnHt	|d\}}|dk	r|g|dd<|t
|g|jtdW5d}~XYnX|r|ddkr|dd}d|_t	|d\}}|
||jtd|r|tdd	|d
d}q||fS)a address_list = (address *("," address)) / obs-addr-list
        obs-addr-list = *([CFWS] ",") address *("," [address / CFWS])

    We depart from the formal grammar here by continuing to parse until the end
    of the input, assuming the input to be entirely composed of an
    address-list.  This is always true in email parsing, and allows us
    to skip invalid addresses to parse additional valid ones.

    Nrrz"address-list entry with no contentzinvalid address in address-listzempty element in address-listrrrr)rqrarhrrr3r4rr>r\r{rrDr4r)rZaddress_listr6errr;rrrrget_address_listsX








rccCst}|std||ddkr6td||tdd|dd}t|\}}|||rx|ddkrtd	||tdd
||ddfS)z& no-fold-literal = "[" *dtext "]"
    z'expected no-fold-literal but found '{}'rrLz;expected '[' at the start of no-fold-literal but found '{}'zno-fold-literal-startrNrHz9expected ']' at the end of no-fold-literal but found '{}'zno-fold-literal-end)rrrr*rhrrG)rZno_fold_literalr6rrrget_no_fold_literals.
rdcCst}|r,|dtkr,t|\}}|||r<|ddkrLtd||tdd|dd}zt|\}}Wn`tjk
rz"t	|\}}|j
tdWn&tjk
rtd|YnXYnX|||r|dd	kr@|j
td
|r8|ddkr8|tdd|dd}||fS|td	d
|dd}zt|\}}Wntjk
rzt
|\}}Wnrtjk
r}zPz"t|\}}|j
tdWn(tjk
rtd|YnXW5d}~XYnXYnX|||r6|ddkr6|dd}n|j
td|tdd|r|dtkrt|\}}||||fS)zmsg-id = [CFWS] "<" id-left '@' id-right  ">" [CFWS]
       id-left = dot-atom-text / obs-id-left
       id-right = dot-atom-text / no-fold-literal / obs-id-right
       no-fold-literal = "[" *dtext "]"
    rrUzexpected msg-id but found '{}'zmsg-id-startrNzobsolete id-left in msg-idz4expected dot-atom-text or obs-id-left but found '{}'rzmsg-id with no id-rightrVz
msg-id-endrOzobsolete id-right in msg-idzFexpected dot-atom-text, no-fold-literal or obs-id-right but found '{}'zmissing trailing '>' on msg-id)rr3r4rhrrr*rr8rBrr>rrdrN)rZmsg_idr6errr
get_msg_ids~






"


rfc
Cst}zt|\}}||WnLtjk
rl}z,t|}t|}|jtd	|W5d}~XYnX|r|jtd	||S)z2message-id      =   "Message-ID:" msg-id CRLF
    zInvalid msg-id: {!r}NzUnexpected {!r})
rrfrhrrr(rrrr*)rZ
message_idr6Zexrrrparse_message_idIs
rgcCst}|s |jtd|S|dtkrXt|\}}|||sX|jtdd}|r|ddkr|dtkr||d7}|dd}q\|s|jtd	||t
|d	nt||_|t
|d
|r|dtkrt|\}}|||r|ddkrT|jdk	r:|jtd|rP|t
|d	|S|t
dd|dd}|r|dtkrt|\}}|||s|jdk	r|jtd|Sd}|r|dtkr||d7}|dd}q|s*|jtd
	||t
|d	nt||_
|t
|d
|rn|dtkrnt|\}}|||r|jtd|t
|d	|S)zE mime-version = [CFWS] 1*digit [CFWS] "." [CFWS] 1*digit [CFWS]

    z%Missing MIME version number (eg: 1.0)rz0Expected MIME version number but found only CFWSrrrNz1Expected MIME major version number but found {!r}r
digitsz0Incomplete MIME version; found only major numberzversion-separatorz1Expected MIME minor version number but found {!r}z'Excess non-CFWS text after MIME version)rrrhrHeaderMissingRequiredValuer3r4isdigitrr*rintrr)rZmime_versionr6rhrrrparse_mime_versiones













rlcCsdt}|r\|ddkr\|dtkrD|t|dd|dd}qt|\}}||q||fS)z Read everything up to the next ';'.

    This is outside the formal grammar.  The InvalidParameter TokenList that is
    returned acts like a Parameter, but the data attributes are None.

    rr]rFrN)rr=rhrr?)rZinvalid_parameterr6rrrget_invalid_parametersrmcCsNt|}|std||}|t|d}t|d}t|||fS)a8ttext = <matches _ttext_matcher>

    We allow any non-TOKEN_ENDS in ttext, but add defects to the token's
    defects list if we find non-ttext characters.  We also register defects for
    *any* non-printables even though the RFC doesn't exclude all of them,
    because we follow the spirit of RFC 5322.

    zexpected ttext but found '{}'Nttext)_non_token_end_matcherrrr*r|rrr)rr/rnrrr	get_ttexts	
rpcCst}|r,|dtkr,t|\}}|||rL|dtkrLtd|t|\}}|||r|dtkrt|\}}||||fS)ztoken = [CFWS] 1*ttext [CFWS]

    The RFC equivalent of ttext is any US-ASCII chars except space, ctls, or
    tspecials.  We also exclude tabs even though the RFC doesn't.

    The RFC implies the CFWS but is not explicit about it in the BNF.

    rexpected token but found '{}')	r\r3r4rh
TOKEN_ENDSrrr*rp)rZmtokenr6rrr	get_tokens	


rscCsNt|}|std||}|t|d}t|d}t|||fS)aQattrtext = 1*(any non-ATTRIBUTE_ENDS character)

    We allow any non-ATTRIBUTE_ENDS in attrtext, but add defects to the
    token's defects list if we find non-attrtext characters.  We also register
    defects for *any* non-printables even though the RFC doesn't exclude all of
    them, because we follow the spirit of RFC 5322.

    z expected attrtext but found {!r}Nr)_non_attribute_end_matcherrrr*r|rrrrr/rrrrget_attrtexts	
rvcCst}|r,|dtkr,t|\}}|||rL|dtkrLtd|t|\}}|||r|dtkrt|\}}||||fS)aH [CFWS] 1*attrtext [CFWS]

    This version of the BNF makes the CFWS explicit, and as usual we use a
    value terminal for the actual run of characters.  The RFC equivalent of
    attrtext is the token characters, with the subtraction of '*', "'", and '%'.
    We include tab in the excluded set just as we do for token.

    rrq)	rr3r4rhATTRIBUTE_ENDSrrr*rvrrr6rrr
get_attributes	


rycCsNt|}|std||}|t|d}t|d}t|||fS)zattrtext = 1*(any non-ATTRIBUTE_ENDS character plus '%')

    This is a special parsing routine so that we get a value that
    includes % escapes as a single string (which we decode as a single
    string later).

    z)expected extended attrtext but found {!r}Nextended-attrtext)#_non_extended_attribute_end_matcherrrr*r|rrrrurrrget_extended_attrtext	s
r|cCst}|r,|dtkr,t|\}}|||rL|dtkrLtd|t|\}}|||r|dtkrt|\}}||||fS)z [CFWS] 1*extended_attrtext [CFWS]

    This is like the non-extended version except we allow % characters, so that
    we can pick up an encoded value as a single string.

    rrq)	rr3r4rhEXTENDED_ATTRIBUTE_ENDSrrr*r|rxrrrget_extended_attribute!	s


r~cCst}|r|ddkr&td||tdd|dd}|rR|dsbtd|d}|r|dr||d7}|dd}qf|dd	kr|d	kr|jtd
t	||_
|t|d||fS)a6 '*' digits

    The formal BNF is more complicated because leading 0s are not allowed.  We
    check for that and add a defect.  We also assume no CFWS is allowed between
    the '*' and the digits, though the RFC is not crystal clear on that.
    The caller should already have dealt with leading CFWS.

    r*zExpected section but found {}zsection-markerrNz$Expected section number but found {}r0z'section number has an invalid leading 0rh)rrrr*rhrrjrZInvalidHeaderErrorrkr)rrrhrrrget_section7	s,	

rcCst}|stdd}|dtkr0t|\}}|sDtd||ddkr^t|\}}nt|\}}|dk	r|g|dd<||||fS)z  quoted-string / attribute

    z&Expected value but found end of stringNrz Expected value but found only {}r
)	rrrr3r4r*r5r~rh)rvr;r6rrr	get_valueU	s"

rcCst}t|\}}|||r,|ddkrL|jtd|||fS|ddkrz t|\}}d|_||Wntj	k
rYnX|st	d|ddkr|t
dd|dd	}d|_|dd
krt	d|t
d
d|dd	}d	}|r,|dtkr,t
|\}}||d	}|}|jrF|rF|dd
krFt|\}}|j}d}|jdkr|r|ddkrd}n$t|\}}	|	r|	ddkrd}n(zt|\}}	WnYnX|	sd}|r0|jtd|||D](}
|
jdkrg|
d	d	<|
}q*q|}nd	}|jtd|r`|ddkr`d	}nt|\}}|jr|jdkr|r|ddkr|||d	k	r|}||fS|jtd|s|jtd|||d	kr||fSn|d	k	r@|D]}
|
jdkr
q$q
|
jdk||
|
j|_|ddkr^t	d||t
dd|dd	}|r|ddkrt|\}}|||j|_|r|ddkrt	d||t
dd|dd	}|d	k	rdt}|r^|dtkrt|\}}n2|dd
krDt
d
d}|dd	}nt|\}}||q|}nt|\}}|||d	k	r|}||fS)aY attribute [section] ["*"] [CFWS] "=" value

    The CFWS is implied by the RFC but not made explicit in the BNF.  This
    simplified form of the BNF from the RFC is made to conform with the RFC BNF
    through some extra checks.  We do it this way because it makes both error
    recovery and working with the resulting parse tree easier.
    rr]z)Parameter contains name ({}) but no valuerTzIncomplete parameterzextended-parameter-markerrN=zParameter not followed by '='parameter-separatorr
F'z5Quoted string value for extended parameter is invalidrezZParameter marked as extended but appears to have a quoted string value that is non-encodedzcApparent initial-extended-value but attribute was not marked as extended or was not initial sectionz(Missing required charset/lang delimitersrzrz=Expected RFC2231 char/lang encoding delimiter, but found {!r}zRFC2231-delimiterz;Expected RFC2231 char/lang encoding delimiter, but found {}ZDQUOTE)rryrhrrrr*rrrrrr3r4r5rlrrvr|rDrrr`rarrrr,)rrr6r;rZappendtoZqstringZinner_valueZ
semi_validr trrrr
get_parameterk	s























rc
Csjt}|rfzt|\}}||Wntjk
r}zd}|dtkrVt|\}}|sp|||WYxS|ddkr|dk	r|||jtdn@t	|\}}|r|g|dd<|||jtd
|W5d}~XYnX|rD|ddkrD|d}d|_t	|\}}|||jtd
||r|t
dd	|d
d}q|S)a! parameter *( ";" parameter )

    That BNF is meant to indicate this routine should only be called after
    finding and handling the leading ';'.  There is no corresponding rule in
    the formal RFC grammar, but it is more convenient for us for the set of
    parameters to be treated as its own TokenList.

    This is 'parse' routine because it consumes the remaining value, but it
    would never be called to parse a full header.  Instead it is called to
    parse everything after the non-parameter value of a specific MIME header.

    Nrr]zparameter entry with no contentzinvalid parameter {!r}rrz)parameter with invalid trailing text {!r}rr)rrrhrrr3r4rrrmr*rDr4r)rZmime_parametersr6rbr;rrrrparse_mime_parameters	sJ







rcCs|rV|ddkrV|dtkr>|t|dd|dd}qt|\}}||q|s^dS|tdd|t|dddS)zBDo our best to find the parameters in an invalid MIME header

    rr]rFrNr)r=rhrr?r)Z	tokenlistrr6rrr_find_mime_parameters-
src
Cst}d}|s$|jtd|Szt|\}}Wn<tjk
rp|jtd|t	|||YSX|||r|ddkr|jtd|rt	|||S|j
|_
|tdd|dd	}zt|\}}Wn>tjk
r*|jtd
|t	|||YSX|||j
|_|sP|S|ddkr|jtd||`
|`t	|||S|tdd
|t|dd	|S)z maintype "/" subtype *( ";" parameter )

    The maintype and substype are tokens.  Theoretically they could
    be checked against the official IANA list + x-token, but we
    don't do that.
    Fz"Missing content type specificationz(Expected content maintype but found {!r}rrzInvalid content typezcontent-type-separatorrNz'Expected content subtype but found {!r}r]z<Only parameters are valid after content type, but found {!r}r)rrrhrrirsrrr*rrrlowerrrrr)rZctypeZrecoverr6rrrparse_content_type_header=
sd












rc
Cst}|s |jtd|Szt|\}}Wn<tjk
rl|jtd|t	|||YSX|||j
|_
|s|S|ddkr|jtd|t	|||S|tdd|t|dd|S)	z* disposition-type *( ";" parameter )

    zMissing content dispositionz+Expected content disposition but found {!r}rr]zCOnly parameters are valid after content disposition, but found {!r}rrN)rrrhrrirsrrr*rrrrrrr)rZdisp_headerr6rrr parse_content_disposition_headerv
s:






rc
Cst}|s |jtd|Szt|\}}Wn.tjk
r^|jtd|YnX|||j	
|_|s|S|r|jtd|dt
kr|t|dd|dd}qt|\}}||q|S)z mechanism

    z!Missing content transfer encodingz1Expected content transfer encoding but found {!r}z*Extra text after content transfer encodingrrFrN)rrrhrrirsrrr*rrrr_r=rr?)rZ
cte_headerr6rrr&parse_content_transfer_encoding_header
s4



rcCsDd}|r@|dr@|ddtkr@|dd}|ddd|d<|S)Nrr)r)linesZwsprrr_steal_trailing_WSP_if_exists
s
rcCs|jp
tj}|jrdnd}dg}d}d}d}tdd}t|}	|	r|	d}
|
|kr`|d8}q>t|
}|
jd	krt	|t
@rd
}z|||}Wn6tk
rt
dd|
jDrd
}nd}d
}YnX|
jdkrt|
|||q>|r|s|
jspd}d}|
jrp|
j|ddt|j}
|j|
krpt|
|t|dkr^t|}|||d|
7<q>t|
dst|
|	}	nt|||||
j|}d}q>t||t|dkr|d|7<q>|
jrt|d|krt|}|s|
r|||d}q>t|
dsNt|
}|
jsD|d7}||||	}	q>|
jrn|sn|	d|
d
}q>t|}|s|
r|||q>|d|7<q>|j||jS)zLReturn string of contents of parse_tree folded according to RFC rules.

    utf-8rrNrFwrap_as_ew_blockedrrTcss|]}t|tjVqdSr)rrrr rrrr#
sz%_refold_parse_tree.<locals>.<genexpr>unknown-8bitrr7rrC)Zmax_line_lengthsysmaxsizeutf8rrrr
rDrr:rCrrZr-_fold_mime_parametersr1rHr;rrrrhrE_fold_as_ewrIr0insertr%)Z
parse_treer8maxlenrrlast_ewrZ
want_encodingZend_ew_not_allowedrr2tstrr`Zencoded_partnewlineZnewpartsrrrr9
s







r9cCs|dk	r<|r<tt|d|d|}|dd||d<|dtkr|d}|dd}t|d|krz|t||d|7<d}|dtkr|d}|dd}|dkrt|dn|}|dkrdn|}	t|	d}
|
d|krtd	|r|t|d}||
}|dkr,|d
q|d|}
tj	|
|	d}t||}|dkr|
dd}
tj	|
|	d}t||}qR|d|7<|t|
d}|r|d
t|d}q|d|7<|r|SdS)aFold string to_encode into lines as encoded word, combining if allowed.
    Return the new value for last_ew, or None if ew_combine_allowed is False.

    If there is already an encoded word in the last line of lines (indicated by
    a non-None value for last_ew) and ew_combine_allowed is true, decode the
    existing ew, combine it with to_encode, and re-encode.  Otherwise, encode
    to_encode.  In either case, split to_encode as necessary so that the
    encoded segments fit within maxlen.

    Nrrrrrrz3max_line_length is too small to fit an encoded wordrN)r`)
r
r(rrrhrrrrrC)Z	to_encoderrrrIr`Zleading_wspZtrailing_wspZnew_last_ewZ	encode_as
chrome_lenZremaining_spaceZ
text_spaceZto_encode_wordZencoded_wordZexcessrrrr1sT



rc	Cs|jD]\}}|dds2|dd7<|}d}z||d}Wn0tk
r|d}t|rtd}d}nd}YnX|rtjj	|d	|d
}	d
|||	}
nd
|t|}
t|dt|
d
|kr|dd|
|d<qn"t|
d|kr
|
d|
qd}|d}|rt|tt|dt|}
||
dkrLd}||
d}}|d|}tjj	|d	|d
}	t|	|krq|d
8}q\|
d
||||	d	}|d
7}||d}|r|dd7<qqdS)a>Fold TokenList 'part' into the 'lines' list as mime parameters.

    Using the decoded list of parameters and values, format them according to
    the RFC rules, including using RFC2231 encoding if the value cannot be
    expressed in 'encoding' and/or the parameter+value is too long to fit
    within 'maxlen'.

    rr]strictFTrrrr)Zsaferz
{}*={}''{}rrrNrrz''rNNz {}*{}*={}{})rrrrCrrrrrror*rrrhr
)r2rrrrrr`Z
error_handlerZencoding_requiredZ
encoded_valuerrZextra_chromerZ
splitpointZmaxcharspartialrrrrrsn


 r)rrerrstringroperatorrZemailrrrrrrr3r:r6rr=Z	TSPECIALSrrZ	ASPECIALSrwr}rcompileVERBOSE	MULTILINEr$rrrLrRrUrWrXrZr\r]rbrmrnrqr{rrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrrr
rrrrrrrrRrSr*r%rrrmatchr.findallr	rortr{rrrr"r(r+r,r0r1r2r4r5r7r8r9r<r?rErBrGrKrMrNrPrTrWrXrYr[r\r^r_r`rarcrdrfrgrlrmrprsrvryr|r~rrrrrrrrrr9rrrrrr<module>s.E
C"	
!*$
V	+






1C+
"&'/'&).9%7ED49/gA